Merge tag 'v4.19.29' into dev-4.19dev-4.19

This is the 4.19.29 stable release

Signed-off-by: Joel Stanley <joel@jms.id.au>

14 files changed, 104 insertions, 33 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 44551d96eaa4..45d5ef8dd0a8 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1661,6 +1661,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 	struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
 	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
 	__poll_t mask = key_to_poll(key);
+	unsigned long flags;
 
 	req->woken = true;
 
@@ -1669,10 +1670,15 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 		if (!(mask & req->events))
 			return 0;
 
-		/* try to complete the iocb inline if we can: */
-		if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
+		/*
+		 * Try to complete the iocb inline if we can. Use
+		 * irqsave/irqrestore because not all filesystems (e.g. fuse)
+		 * call this function with IRQs disabled and because IRQs
+		 * have to be disabled before ctx_lock is obtained.
+		 */
+		if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
 			list_del(&iocb->ki_list);
-			spin_unlock(&iocb->ki_ctx->ctx_lock);
+			spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags);
 
 			list_del_init(&req->wait.entry);
 			aio_poll_complete(iocb, mask);
diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c
index d441244b79df..28d9c2b1b3bb 100644
--- a/fs/autofs/expire.c
+++ b/fs/autofs/expire.c
@@ -596,7 +596,6 @@ int autofs_expire_run(struct super_block *sb,
 	pkt.len = dentry->d_name.len;
 	memcpy(pkt.name, dentry->d_name.name, pkt.len);
 	pkt.name[pkt.len] = '\0';
-	dput(dentry);
 
 	if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)))
 		ret = -EFAULT;
@@ -609,6 +608,8 @@ int autofs_expire_run(struct super_block *sb,
 	complete_all(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
 
+	dput(dentry);
+
 	return ret;
 }
 
diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c
index 846c052569dd..3c14a8e45ffb 100644
--- a/fs/autofs/inode.c
+++ b/fs/autofs/inode.c
@@ -255,8 +255,10 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
 	}
 	root_inode = autofs_get_inode(s, S_IFDIR | 0755);
 	root = d_make_root(root_inode);
-	if (!root)
+	if (!root) {
+		ret = -ENOMEM;
 		goto fail_ino;
+	}
 	pipe = NULL;
 
 	root->d_fsdata = ino;
diff --git a/fs/buffer.c b/fs/buffer.c
index 6f1ae3ac9789..c083c4b3c1e7 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -200,6 +200,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	struct buffer_head *head;
 	struct page *page;
 	int all_mapped = 1;
+	static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1);
 
 	index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
 	page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED);
@@ -227,15 +228,15 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	 * file io on the block device and getblk.  It gets dealt with
 	 * elsewhere, don't buffer_error if we had some unmapped buffers
 	 */
-	if (all_mapped) {
-		printk("__find_get_block_slow() failed. "
-			"block=%llu, b_blocknr=%llu\n",
-			(unsigned long long)block,
-			(unsigned long long)bh->b_blocknr);
-		printk("b_state=0x%08lx, b_size=%zu\n",
-			bh->b_state, bh->b_size);
-		printk("device %pg blocksize: %d\n", bdev,
-			1 << bd_inode->i_blkbits);
+	ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE);
+	if (all_mapped && __ratelimit(&last_warned)) {
+		printk("__find_get_block_slow() failed. block=%llu, "
+		       "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, "
+		       "device %pg blocksize: %d\n",
+		       (unsigned long long)block,
+		       (unsigned long long)bh->b_blocknr,
+		       bh->b_state, bh->b_size, bdev,
+		       1 << bd_inode->i_blkbits);
 	}
 out_unlock:
 	spin_unlock(&bd_mapping->private_lock);
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 1e5a1171212f..a2d701775c49 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2243,10 +2243,12 @@ SMB2_open_free(struct smb_rqst *rqst)
 {
 	int i;
 
-	cifs_small_buf_release(rqst->rq_iov[0].iov_base);
-	for (i = 1; i < rqst->rq_nvec; i++)
-		if (rqst->rq_iov[i].iov_base != smb2_padding)
-			kfree(rqst->rq_iov[i].iov_base);
+	if (rqst && rqst->rq_iov) {
+		cifs_small_buf_release(rqst->rq_iov[0].iov_base);
+		for (i = 1; i < rqst->rq_nvec; i++)
+			if (rqst->rq_iov[i].iov_base != smb2_padding)
+				kfree(rqst->rq_iov[i].iov_base);
+	}
 }
 
 int
@@ -2535,7 +2537,8 @@ SMB2_close_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
 void
 SMB2_close_free(struct smb_rqst *rqst)
 {
-	cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
+	if (rqst && rqst->rq_iov)
+		cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
 }
 
 int
@@ -2685,7 +2688,8 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
 void
 SMB2_query_info_free(struct smb_rqst *rqst)
 {
-	cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
+	if (rqst && rqst->rq_iov)
+		cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
 }
 
 static int
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 8fb7887f2b3d..437257d1116f 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -84,8 +84,8 @@
 
 #define NUMBER_OF_SMB2_COMMANDS	0x0013
 
-/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */
-#define MAX_SMB2_HDR_SIZE 0x00b0
+/* 52 transform hdr + 64 hdr + 88 create rsp */
+#define MAX_SMB2_HDR_SIZE 204
 
 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
 #define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd)
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 82377017130f..d31b6c72b476 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -21,8 +21,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 	spin_lock(&sb->s_inode_list_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		spin_lock(&inode->i_lock);
+		/*
+		 * We must skip inodes in unusual state. We may also skip
+		 * inodes without pages but we deliberately won't in case
+		 * we need to reschedule to avoid softlockups.
+		 */
 		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
-		    (inode->i_mapping->nrpages == 0)) {
+		    (inode->i_mapping->nrpages == 0 && !need_resched())) {
 			spin_unlock(&inode->i_lock);
 			continue;
 		}
@@ -30,6 +35,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 		spin_unlock(&inode->i_lock);
 		spin_unlock(&sb->s_inode_list_lock);
 
+		cond_resched();
 		invalidate_mapping_pages(inode->i_mapping, 0, -1);
 		iput(toput_inode);
 		toput_inode = inode;
diff --git a/fs/exec.c b/fs/exec.c
index 1ebf6e5a521d..433b1257694a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -929,7 +929,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 		bytes = kernel_read(file, *buf + pos, i_size - pos, &pos);
 		if (bytes < 0) {
 			ret = bytes;
-			goto out;
+			goto out_free;
 		}
 
 		if (bytes == 0)
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 4614ee25f621..9d566e62684c 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -107,7 +107,7 @@ static int glock_wake_function(wait_queue_entry_t *wait, unsigned int mode,
 
 static wait_queue_head_t *glock_waitqueue(struct lm_lockname *name)
 {
-	u32 hash = jhash2((u32 *)name, sizeof(*name) / 4, 0);
+	u32 hash = jhash2((u32 *)name, ht_parms.key_len / 4, 0);
 
 	return glock_wait_table + hash_32(hash, GLOCK_WAIT_TABLE_BITS);
 }
diff --git a/fs/iomap.c b/fs/iomap.c
index e57fb1e534c5..fac45206418a 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -117,6 +117,12 @@ iomap_page_create(struct inode *inode, struct page *page)
 	atomic_set(&iop->read_count, 0);
 	atomic_set(&iop->write_count, 0);
 	bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);
+
+	/*
+	 * migrate_page_move_mapping() assumes that pages with private data have
+	 * their count elevated by 1.
+	 */
+	get_page(page);
 	set_page_private(page, (unsigned long)iop);
 	SetPagePrivate(page);
 	return iop;
@@ -133,6 +139,7 @@ iomap_page_release(struct page *page)
 	WARN_ON_ONCE(atomic_read(&iop->write_count));
 	ClearPagePrivate(page);
 	set_page_private(page, 0);
+	put_page(page);
 	kfree(iop);
 }
 
@@ -565,8 +572,10 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage,
 
 	if (page_has_private(page)) {
 		ClearPagePrivate(page);
+		get_page(newpage);
 		set_page_private(newpage, page_private(page));
 		set_page_private(page, 0);
+		put_page(page);
 		SetPagePrivate(newpage);
 	}
 
@@ -1778,6 +1787,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	loff_t pos = iocb->ki_pos, start = pos;
 	loff_t end = iocb->ki_pos + count - 1, ret = 0;
 	unsigned int flags = IOMAP_DIRECT;
+	bool wait_for_completion = is_sync_kiocb(iocb);
 	struct blk_plug plug;
 	struct iomap_dio *dio;
 
@@ -1797,7 +1807,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->end_io = end_io;
 	dio->error = 0;
 	dio->flags = 0;
-	dio->wait_for_completion = is_sync_kiocb(iocb);
 
 	dio->submit.iter = iter;
 	dio->submit.waiter = current;
@@ -1852,7 +1861,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		dio_warn_stale_pagecache(iocb->ki_filp);
 	ret = 0;
 
-	if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion &&
+	if (iov_iter_rw(iter) == WRITE && !wait_for_completion &&
 	    !inode->i_sb->s_dio_done_wq) {
 		ret = sb_init_dio_done_wq(inode->i_sb);
 		if (ret < 0)
@@ -1868,7 +1877,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		if (ret <= 0) {
 			/* magic error code to fall back to buffered I/O */
 			if (ret == -ENOTBLK) {
-				dio->wait_for_completion = true;
+				wait_for_completion = true;
 				ret = 0;
 			}
 			break;
@@ -1890,8 +1899,24 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (dio->flags & IOMAP_DIO_WRITE_FUA)
 		dio->flags &= ~IOMAP_DIO_NEED_SYNC;
 
+	/*
+	 * We are about to drop our additional submission reference, which
+	 * might be the last reference to the dio.  There are three three
+	 * different ways we can progress here:
+	 *
+	 *  (a) If this is the last reference we will always complete and free
+	 *	the dio ourselves.
+	 *  (b) If this is not the last reference, and we serve an asynchronous
+	 *	iocb, we must never touch the dio after the decrement, the
+	 *	I/O completion handler will complete and free it.
+	 *  (c) If this is not the last reference, but we serve a synchronous
+	 *	iocb, the I/O completion handler will wake us up on the drop
+	 *	of the final reference, and we will complete and free it here
+	 *	after we got woken by the I/O completion handler.
+	 */
+	dio->wait_for_completion = wait_for_completion;
 	if (!atomic_dec_and_test(&dio->ref)) {
-		if (!dio->wait_for_completion)
+		if (!wait_for_completion)
 			return -EIOCBQUEUED;
 
 		for (;;) {
@@ -1908,9 +1933,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		__set_current_state(TASK_RUNNING);
 	}
 
-	ret = iomap_dio_complete(dio);
-
-	return ret;
+	return iomap_dio_complete(dio);
 
 out_free_dio:
 	kfree(dio);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 5ef2c71348bd..6b666d187907 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1906,6 +1906,11 @@ static int nfs_parse_devname(const char *dev_name,
 	size_t len;
 	char *end;
 
+	if (unlikely(!dev_name || !*dev_name)) {
+		dfprintk(MOUNT, "NFS: device name not specified\n");
+		return -EINVAL;
+	}
+
 	/* Is the host name protected with square brakcets? */
 	if (*dev_name == '[') {
 		end = strchr(++dev_name, ']');
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 8ae109429a88..e39bac94dead 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -256,7 +256,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
 		inode = proc_get_inode(dir->i_sb, de);
 		if (!inode)
 			return ERR_PTR(-ENOMEM);
-		d_set_d_op(dentry, &proc_misc_dentry_ops);
+		d_set_d_op(dentry, de->proc_dops);
 		return d_splice_alias(inode, dentry);
 	}
 	read_unlock(&proc_subdir_lock);
@@ -429,6 +429,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 	INIT_LIST_HEAD(&ent->pde_openers);
 	proc_set_user(ent, (*parent)->uid, (*parent)->gid);
 
+	ent->proc_dops = &proc_misc_dentry_ops;
+
 out:
 	return ent;
 }
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 5185d7f6a51e..95b14196f284 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -44,6 +44,7 @@ struct proc_dir_entry {
 	struct completion *pde_unload_completion;
 	const struct inode_operations *proc_iops;
 	const struct file_operations *proc_fops;
+	const struct dentry_operations *proc_dops;
 	union {
 		const struct seq_operations *seq_ops;
 		int (*single_show)(struct seq_file *, void *);
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index d5e0fcb3439e..a7b12435519e 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -38,6 +38,22 @@ static struct net *get_proc_net(const struct inode *inode)
 	return maybe_get_net(PDE_NET(PDE(inode)));
 }
 
+static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	return 0;
+}
+
+static const struct dentry_operations proc_net_dentry_ops = {
+	.d_revalidate	= proc_net_d_revalidate,
+	.d_delete	= always_delete_dentry,
+};
+
+static void pde_force_lookup(struct proc_dir_entry *pde)
+{
+	/* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
+	pde->proc_dops = &proc_net_dentry_ops;
+}
+
 static int seq_open_net(struct inode *inode, struct file *file)
 {
 	unsigned int state_size = PDE(inode)->state_size;
@@ -90,6 +106,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
+	pde_force_lookup(p);
 	p->proc_fops = &proc_net_seq_fops;
 	p->seq_ops = ops;
 	p->state_size = state_size;
@@ -133,6 +150,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
+	pde_force_lookup(p);
 	p->proc_fops = &proc_net_seq_fops;
 	p->seq_ops = ops;
 	p->state_size = state_size;
@@ -181,6 +199,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
+	pde_force_lookup(p);
 	p->proc_fops = &proc_net_single_fops;
 	p->single_show = show;
 	return proc_register(parent, p);
@@ -223,6 +242,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
+	pde_force_lookup(p);
 	p->proc_fops = &proc_net_single_fops;
 	p->single_show = show;
 	p->write = write;